Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.9685. Min Act: -0.1700
Data Index: 1613616 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8492. Min Act: -0.1700
Data Index: 3201253 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8492. Min Act: -0.1700
Data Index: 419195 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8321. Min Act: -0.1700
Data Index: 7960551 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 7453338 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8149. Min Act: -0.1700
Data Index: 636491 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8149. Min Act: -0.1700
Data Index: 7092549 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8149. Min Act: -0.1700
Data Index: 2348507 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 2751370 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 4867919 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1699
Data Index: 5914094 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 1249949 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 691725 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7891. Min Act: -0.1700
Data Index: 419772 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7977. Min Act: -0.1700
Data Index: 6190426 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.8149. Min Act: -0.1700
Data Index: 1658524 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7891. Min Act: -0.1700
Data Index: 349279 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7891. Min Act: -0.1700
Data Index: 6794053 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7805. Min Act: -0.1700
Data Index: 5612729 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9685. Min Range: -1.9685
Max Act: 1.7805. Min Act: -0.1700
Data Index: 231070 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19